{"id":33185489,"url":"https://github.com/adammpkins/llama-terminal-completion","last_synced_at":"2026-04-03T18:13:11.973Z","repository":{"id":188858218,"uuid":"679558381","full_name":"adammpkins/llama-terminal-completion","owner":"adammpkins","description":"AI terminal assistant for any OpenAI-compatible API. Features interactive chat TUI, command generation, code explanation, and streaming responses. Works with Ollama, OpenAI, LM Studio, and more.","archived":false,"fork":false,"pushed_at":"2025-12-08T05:59:46.000Z","size":445,"stargazers_count":190,"open_issues_count":2,"forks_count":11,"subscribers_count":5,"default_branch":"main","last_synced_at":"2025-12-09T14:24:51.981Z","etag":null,"topics":["ai","inference","llm","python"],"latest_commit_sha":null,"homepage":"https://adammpkins.github.io/llamaterm/","language":"Go","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/adammpkins.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2023-08-17T05:43:37.000Z","updated_at":"2025-12-08T05:59:50.000Z","dependencies_parsed_at":"2024-01-07T21:02:13.827Z","dependency_job_id":"f897ddd1-9887-4679-be5a-683e4ce32fcf","html_url":"https://github.com/adammpkins/llama-terminal-completion","commit_stats":null,"previous_names":["adammpkins/llama-terminal-completion"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/adammpkins/llama-terminal-completion","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adammpkins%2Fllama-terminal-completion","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adammpkins%2Fllama-terminal-completion/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adammpkins%2Fllama-terminal-completion/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adammpkins%2Fllama-terminal-completion/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/adammpkins","download_url":"https://codeload.github.com/adammpkins/llama-terminal-completion/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/adammpkins%2Fllama-terminal-completion/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31368162,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-03T17:53:18.093Z","status":"ssl_error","status_checked_at":"2026-04-03T17:53:17.617Z","response_time":107,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","inference","llm","python"],"created_at":"2025-11-16T05:00:20.092Z","updated_at":"2026-04-03T18:13:11.956Z","avatar_url":"https://github.com/adammpkins.png","language":"Go","funding_links":[],"categories":["\u003ca name=\"copilot\"\u003e\u003c/a\u003eCo-pilot"],"sub_categories":[],"readme":"# LlamaTerm\n\n![LlamaTerm Logo](old-project/llama-md.png)\n\n**AI assistant in your terminal** — works with any OpenAI-compatible API.\n\n```bash\nlt ask \"How do I find large files in Linux?\"\nlt cmd \"compress all images in this folder\"\n```\n\n## Features\n\n- 🚀 **Fast** — Single Go binary, \u003c100ms startup\n- 🔌 **Universal** — Works with Ollama, LM Studio, OpenAI, and more\n- 💬 **Streaming** — Real-time response display\n- 🛡️ **Safe** — Command confirmation with dangerous command detection\n- ⚙️ **Configurable** — Config files, env vars, or CLI flags\n\n## Quick Start\n\n### Install\n\n```bash\n# Quick install (requires Go)\ncurl -sSL https://raw.githubusercontent.com/adammpkins/llama-terminal-completion/main/install.sh | bash\n\n# Or build from source\ngit clone https://github.com/adammpkins/llama-terminal-completion.git\ncd llamaterm\nmake install\n```\n\n### Shell Completion\n\n```bash\n# Bash\nlt completion bash \u003e /usr/local/etc/bash_completion.d/lt\n\n# Zsh (add to ~/.zshrc)\nsource \u003c(lt completion zsh)\n\n# Fish\nlt completion fish \u003e ~/.config/fish/completions/lt.fish\n```\n\n### Usage\n\n```bash\n# Ask questions\nlt ask \"What is the difference between TCP and UDP?\"\n\n# Generate shell commands\nlt cmd \"find all .go files modified in the last week\"\n\n# Pipe content\ncat error.log | lt ask \"What's wrong here?\"\n```\n\n### Configuration\n\nLlamaTerm works out of the box with [Ollama](https://ollama.ai) running on localhost.\n\nFor other providers, configure via:\n\n1. **Config file** (`~/.config/lt/config.yaml`):\n```yaml\nbase_url: https://api.openai.com/v1\nmodel: gpt-4o-mini\napi_key: sk-...\n```\n\n2. **Environment variables**:\n```bash\nexport LT_BASE_URL=https://api.openai.com/v1\nexport LT_MODEL=gpt-4o-mini\nexport LT_API_KEY=sk-...\n# or\nexport OPENAI_API_KEY=sk-...\n```\n\n3. **CLI flags**:\n```bash\nlt --base-url https://api.openai.com/v1 --model gpt-4o ask \"Hello\"\n```\n\n## Supported Providers\n\n| Provider | Base URL | Notes |\n|----------|----------|-------|\n| Ollama | `http://localhost:11434/v1` | Default, no API key needed |\n| LM Studio | `http://localhost:1234/v1` | Local GUI-based |\n| llama.cpp | `http://localhost:8080/v1` | llama.cpp server |\n| OpenAI | `https://api.openai.com/v1` | Requires API key |\n| Azure OpenAI | Custom | Requires configuration |\n\n## Commands\n\n| Command | Description |\n|---------|-------------|\n| `lt ask \u003cquestion\u003e` | Ask a question (`-c` to copy) |\n| `lt cmd \u003cdescription\u003e` | Generate a shell command |\n| `lt quick \u003cdescription\u003e` | Generate and run immediately |\n| `lt copy \u003cquestion\u003e` | Ask and copy to clipboard |\n| `lt chat` | Interactive chat session |\n| `lt explain \u003cfile\u003e` | Explain code or file contents |\n| `lt fix \u003cerror\u003e` | Get help fixing an error |\n| `lt config show` | Show current configuration |\n| `lt config init` | Create config file |\n| `lt history list` | View saved conversations |\n| `lt version` | Show version info |\n\n### Command Flags\n\n```\nGlobal:\n  --base-url    API base URL\n  --api-key     API key\n  -m, --model   Model to use\n  --no-stream   Disable streaming output\n  --max-tokens  Maximum tokens to generate\n  --temperature Temperature for generation\n\nlt cmd:\n  --dry-run     Show command without running\n  -y, --yes     Run without confirmation\n```\n\n## More Examples\n\n```bash\n# Interactive chat with memory\nlt chat\n\n# Analyze a file\nlt explain main.go\nlt explain config.yaml \"What does this configure?\"\n\n# Debug errors\nlt fix \"Error: module not found\"\nnpm run build 2\u003e\u00261 | lt fix\n```\n\n## Development\n\n```bash\n# Download dependencies\nmake deps\n\n# Build\nmake build\n\n# Run tests\nmake test\n\n# Run\n./bin/lt ask \"Hello\"\n```\n\n## License\n\nMIT License\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadammpkins%2Fllama-terminal-completion","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fadammpkins%2Fllama-terminal-completion","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadammpkins%2Fllama-terminal-completion/lists"}